Posts
Comments
Dall-e 2 is so mean to me lol. I like the dresses though, especially on the bottom far-left. If you can send me that and the fourth one on the top I will be happy, thank you (going to try to edit it on photoshop or something)
I tried fixing the prompt you can try seeing if it will work this time
"White haired girl wearing white tights with a girl with black hair wearing opaque black tights and blushing, Anime fanart, danbooru, deviantart, advanced digital art settings"
(since there is 2 girls, it doesn't qualify as "explicit" and more just anime fanart)
Yes, it looks like it has some concept of the game. Tell me how it goes with changing the wording
Prompt from my brother:
What people from 1920 thought 2020 would look like. 1920's Artist's depiction of 2020
Prompt:
Axis and Allies board game 2022 setup. Digital image official concept
(Remove some words if it doesn't work)
Small white cat wearing a red collar with a bell on it hugging a shadow person. Cute digital art, enhanced digital image
Cute White Cat Plushie On A Bed, 4K resolution, amateur photography
Prompt:
"Chi in Chi's Sweet Home japanese animation. Streaming service Crunchyroll. Screenshot of episode with Chi, who is a cute tabby-white mixed cat. 2D, Google Search Screenshot, Pinterest"
Looking at the boobs on the first picture, I feel like the AI can do it but since it is an anime, it is mixed in with hentai pictures and animal-humans. The AI must get anime animals and humans confused. The sad thing is that the AI knows what Kyubey is but it adds a bunch of random anime context. Maybe it needs words like "pokemon cat" just to understand it's not some sort of catgirl body mixed with kyubey
Yes! Thank you. I also think I will give up trying to get kyubey to generate but maybe whenever I get access I will try more idk
Reference Picture of Kyubey. Drawn By Puella Magi Madoka Magica. Digital Art Clip Studio Paint Anime, Pretty and Shining. Advanced Image of Kyubey. The character is Kyubey from Puella Magi Madoka Magica
Maybe the word specific and exact picture throw it off. This actually makes this type of prompt very helpful for product / character design
The third on the top is very cute
Check out this post I found.
A Cute Cat Creature Character: Kyubey, Anime Show: Puella Magi Madoka Magica, Style: Screenshot From Anime Show. Exact screenshot, no variations from original artwork
It looks like all the other modifiers override the "in the style of chis sweet home" I think the AI needs: "A Cute Cat Creature Character: Kyubey, Anime Show: Puella Magi Madoka Magica, Style: Screenshot From Anime Show. Exact screenshot, no variations from original artwork"
Ohhhh so maybe next prompt we can specify that they are not "anime girls" Also, these are very cute lol. The first one is the most accurate and the fact that the AI understands what Kyubey looks like means that it is probably looking for very specific wording to get it accurate
Prompt Idea:
Exact Picture of Kyubey, 2 Cat Ears, 2 Bunny Ears. Red Eyed Cat Antagonist From Puella Magi Madoka Magica. Specific Puella Magi Madoka Magica Anime Screenshot, No Variations
Since OpenAI optimized it's output for things as you suggested in your article (dresses, animals) I believe hidden in the depths of the AI, it can pull pictures such as Kyubey but requires an un-optimized input (as in broken English or maybe in Japanese for this specific one)
So basically telling an alien what to generate in their own language... And the problem is that we don't know what this is with the information currently available (with tests from DALL-E 1)
So it knows the color-scheme and then tries to make some sort of Pokémon off of it. I think maybe the AI believes it is creating a fictional screenshot concept art type thing. Even when you give it a show to go off of, it doesn't understand what to pull off of. I think whenever I get access to dall-e 2, I will try figuring out key buzz words to give it.
I also think since I added "pixiv" since most of the pictures there are anthropomorphic, it kinda just tagged it in. I believe the prompting is much more complicated than we think and requires further evaluation. There has to be certain phrases in specific orders the AI can use better that the community doesn't know yet.
Suggestion: Can it do Kyubey from Madoka Magica?
-
Kyubey from Madoka Magica, photorealistic, high quality anime, 4K, pixiv, digital picture
-
Kyubey from Madoka Magica swimming in a pool of soul-gems, 4K anime, digital art, pixiv, hyperrealistic beautiful
-
Kyubey from Puella Magi Madoka Magica in the style of Chi's Sweet Home Anime, 4K digital art anime, pixiv
(Feel free to change these around)